benchmark · first seen 16 Oct 2026
ToolSandbox
A benchmark for evaluating tool-using language model agents in stateful, multi-turn interactive scenarios.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Agents' Last Doubt: Knowing When to Act and When to Step Back in Tool-Using AgentsPapers · 16 Oct 2026 · Qisai Liu, Qingyue Jiao, Bangwei Guo, Wenxi Dai, Changyi Yang, Jiahe Liu, Dimitr…
Latest sources
- Agents' Last Doubt: Knowing When to Act and When to Step Back in Tool-Using AgentsPapers · 16 Oct 2026 · Qisai Liu, Qingyue Jiao, Bangwei Guo, Wenxi Dai, Changyi Yang, Jiahe Liu, Dimitr…